© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3268
    Prev
    Next
    INDEX
    Explanations

    Question words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âgées
    -0.62
     esiste
    -0.60
    writeFieldEnd
    -0.59
    yorsunuz
    -0.59
    ülé
    -0.59
     Administrativna
    -0.58
     esistono
    -0.58
    multirow
    -0.58
     exists
    -0.58
     aussieht
    -0.57
    POSITIVE LOGITS
     to
    0.60
    aarrggbb
    0.54
     VIAF
    0.53
     الحره
    0.53
     tell
    0.51
     get
    0.47
     identify
    0.46
    styleable
    0.46
     determine
    0.46
     "$(
    0.45
    Activations Density 0.012%

    No Known Activations